© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22258
    Prev
    Next
    INDEX
    Explanations

    names of places or entities containing the word "Ant" or similar

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific geographical locations and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.75
     tissues
    -0.65
     paralle
    -0.65
    wagen
    -0.62
    respective
    -0.62
    inki
    -0.61
     envelope
    -0.60
     accustomed
    -0.60
     quarters
    -0.60
    GREEN
    -0.59
    POSITIVE LOGITS
    icrobial
    0.81
    illard
    0.79
    ICAN
    0.79
    ritic
    0.75
    rial
    0.74
    ILA
    0.72
    ircraft
    0.70
    ailable
    0.69
    oli
    0.68
    iannopoulos
    0.67
    Activations Density 0.085%

    No Known Activations